Fast-accurate 3D face model generation using a single video camera

Tomoya Hara, Hiroyuki Kubo, Akinobu Maejima, Shigeo Morishima

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    3 Citations (Scopus)

    Abstract

    In this paper, we present a new method to generate a 3D face model, based on both Data-Driven and Structure-from-Motion approach. Considering both 2D frontal face image constraint, 3D geometric constraint, and likelihood constraint, we are able to reconstruct subject's face model accurately, robustly, and automatically. Using our method, it is possible to create a 3D face model in 5.8 [sec] by only shaking own head freely in front of a single video camera.

    Original languageEnglish
    Title of host publicationProceedings - International Conference on Pattern Recognition
    Pages1269-1272
    Number of pages4
    Publication statusPublished - 2012
    Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba
    Duration: 2012 Nov 112012 Nov 15

    Other

    Other21st International Conference on Pattern Recognition, ICPR 2012
    CityTsukuba
    Period12/11/1112/11/15

    Fingerprint

    Video cameras

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition

    Cite this

    Hara, T., Kubo, H., Maejima, A., & Morishima, S. (2012). Fast-accurate 3D face model generation using a single video camera. In Proceedings - International Conference on Pattern Recognition (pp. 1269-1272). [6460370]

    Fast-accurate 3D face model generation using a single video camera. / Hara, Tomoya; Kubo, Hiroyuki; Maejima, Akinobu; Morishima, Shigeo.

    Proceedings - International Conference on Pattern Recognition. 2012. p. 1269-1272 6460370.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Hara, T, Kubo, H, Maejima, A & Morishima, S 2012, Fast-accurate 3D face model generation using a single video camera. in Proceedings - International Conference on Pattern Recognition., 6460370, pp. 1269-1272, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, 12/11/11.
    Hara T, Kubo H, Maejima A, Morishima S. Fast-accurate 3D face model generation using a single video camera. In Proceedings - International Conference on Pattern Recognition. 2012. p. 1269-1272. 6460370
    Hara, Tomoya ; Kubo, Hiroyuki ; Maejima, Akinobu ; Morishima, Shigeo. / Fast-accurate 3D face model generation using a single video camera. Proceedings - International Conference on Pattern Recognition. 2012. pp. 1269-1272
    @inproceedings{bd5d42ce84cc4f4fa9f0c5ab6038bf7b,
    title = "Fast-accurate 3D face model generation using a single video camera",
    abstract = "In this paper, we present a new method to generate a 3D face model, based on both Data-Driven and Structure-from-Motion approach. Considering both 2D frontal face image constraint, 3D geometric constraint, and likelihood constraint, we are able to reconstruct subject's face model accurately, robustly, and automatically. Using our method, it is possible to create a 3D face model in 5.8 [sec] by only shaking own head freely in front of a single video camera.",
    author = "Tomoya Hara and Hiroyuki Kubo and Akinobu Maejima and Shigeo Morishima",
    year = "2012",
    language = "English",
    isbn = "9784990644109",
    pages = "1269--1272",
    booktitle = "Proceedings - International Conference on Pattern Recognition",

    }

    TY - GEN

    T1 - Fast-accurate 3D face model generation using a single video camera

    AU - Hara, Tomoya

    AU - Kubo, Hiroyuki

    AU - Maejima, Akinobu

    AU - Morishima, Shigeo

    PY - 2012

    Y1 - 2012

    N2 - In this paper, we present a new method to generate a 3D face model, based on both Data-Driven and Structure-from-Motion approach. Considering both 2D frontal face image constraint, 3D geometric constraint, and likelihood constraint, we are able to reconstruct subject's face model accurately, robustly, and automatically. Using our method, it is possible to create a 3D face model in 5.8 [sec] by only shaking own head freely in front of a single video camera.

    AB - In this paper, we present a new method to generate a 3D face model, based on both Data-Driven and Structure-from-Motion approach. Considering both 2D frontal face image constraint, 3D geometric constraint, and likelihood constraint, we are able to reconstruct subject's face model accurately, robustly, and automatically. Using our method, it is possible to create a 3D face model in 5.8 [sec] by only shaking own head freely in front of a single video camera.

    UR - http://www.scopus.com/inward/record.url?scp=84874572392&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84874572392&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 9784990644109

    SP - 1269

    EP - 1272

    BT - Proceedings - International Conference on Pattern Recognition

    ER -